Related papers: Good-Enough Example Extrapolation
Given the high computational cost of preference alignment training of large language models (LLMs), exploring efficient methods to reduce the training overhead remains an important and compelling research problem. Motivated by the…
Grammatical Error Correction (GEC) should not focus only on high accuracy of corrections but also on interpretability for language learning. However, existing neural-based GEC models mainly aim at improving accuracy, and their…
In distributed learning, the goal is to perform a learning task over data distributed across multiple nodes with minimal (expensive) communication. Prior work (Daume III et al., 2012) proposes a general model that bounds the communication…
Class-incremental learning aims to learn new classes in an incremental fashion without forgetting the previously learned ones. Several research works have shown how additional data can be used by incremental models to help mitigate…
Data augmentation is a popular pre-processing trick to improve generalization accuracy. It is believed that by processing augmented inputs in tandem with the original ones, the model learns a more robust set of features which are shared…
Stacking, a potent ensemble learning method, leverages a meta-model to harness the strengths of multiple base models, thereby enhancing prediction accuracy. Traditional stacking techniques typically utilize established learning models, such…
Extrapolation in reinforcement learning is the ability to generalize at test time given states that could never have occurred at training time. Here we consider four factors that lead to improved extrapolation in a simple Gridworld…
The Graph Neural Network (GNN) has been widely used for graph data representation. However, the existing researches only consider the ideal balanced dataset, and the imbalanced dataset is rarely considered. Traditional methods such as…
The recent contrastive learning methods, due to their effectiveness in representation learning, have been widely applied to modeling graph data. Random perturbation is widely used to build contrastive views for graph data, which however,…
Position modeling plays a critical role in Transformers. In this paper, we focus on length extrapolation, i.e., training on short texts while evaluating longer sequences. We define attention resolution as an indicator of extrapolation. Then…
Among all data augmentation techniques proposed so far, linear interpolation of training samples, also called Mixup, has found to be effective for a large panel of applications. Along with improved predictive performance, Mixup is also a…
Compositional generalization, the ability to predict complex meanings from training on simpler sentences, poses challenges for powerful pretrained seq2seq models. In this paper, we show that data augmentation methods that sample MRs and…
Accurate modeling is essential in integer-valued real phenomena, including the distribution of entire data, zero-inflated (ZI) data, and discrete exceedances. The Poisson and Negative Binomial distributions, along with their ZI variants,…
Data augmentation is widely used in text classification, especially in the low-resource regime where a few examples for each class are available during training. Despite the success, generating data augmentations as hard positive examples…
Most successful information extraction systems operate with access to a large collection of documents. In this work, we explore the task of acquiring and incorporating external evidence to improve extraction accuracy in domains where the…
Supervised deep learning methods for segmentation require large amounts of labelled training data, without which they are prone to overfitting, not generalizing well to unseen images. In practice, obtaining a large number of annotations…
Out-of-distribution (OOD) generalization deals with the prevalent learning scenario where test distribution shifts from training distribution. With rising application demands and inherent complexity, graph OOD problems call for specialized…
Relation extraction is an important but challenging task that aims to extract all hidden relational facts from the text. With the development of deep language models, relation extraction methods have achieved good performance on various…
Text embeddings, i.e. vector representations of entire texts, play an important role in many NLP applications, such as retrieval-augmented generation, clustering, or visualizing collections of texts for data exploration. Currently,…
Data augmentation is proven to be effective in many NLU tasks, especially for those suffering from data scarcity. In this paper, we present a powerful and easy to deploy text augmentation framework, Data Boost, which augments data through…